Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    被
    -0.07
    lane
    -0.07
     dirig
    -0.06
    -X
    -0.06
    摩
    -0.06
    Wik
    -0.06
    ircon
    -0.06
     mam
    -0.06
    ello
    -0.06
     tx
    -0.06
    POSITIVE LOGITS
     Ген
    0.07
    Porno
    0.06
    bounded
    0.06
     photograph
    0.06
    .Document
    0.06
    нт
    0.06
    "));
    0.06
    (empty
    0.06
     Partisi
    0.06
     Proble
    0.06
    Act Density 0.004%

    No Known Activations